© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 8158
    Prev
    Next
    INDEX
    Explanations

    places names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    etur
    -0.12
     Blink
    -0.11
    prime
    -0.11
     worldwide
    -0.10
     Welch
    -0.10
     Jennings
    -0.10
     Weinstein
    -0.10
    ena
    -0.10
     Mississippi
    -0.10
    (xs
    -0.10
    POSITIVE LOGITS
     Pvt
    0.11
    ensis
    0.10
    iens
    0.09
     LLC
    0.08
    ease
    0.07
    bane
    0.07
    irm
    0.07
     outward
    0.07
     Lyn
    0.07
     intentional
    0.07
    Activations Density 0.898%

    No Known Activations